init sepa-precios-archiver

.github/workflows/sepa-precios-archiver.yml

@@ -0,0 +1,24 @@
+name: Archive Prices
+
+on:
+  schedule:
+    - cron: "0 */12 * * *" # Run every 6 hours
+  workflow_dispatch: # Allow manual trigger
+
+jobs:
+  archive-prices:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v1
+        with:
+          bun-version: latest
+
+      - name: Run archiver script
+        env:
+          GITHUB_TOKEN: ${{ secrets.ARCHIVE_GITHUB_TOKEN }}
+        run: |
+          cd sepa-precios-archiver
+          bun index.ts

sepa-precios-archiver/.gitignore

@@ -0,0 +1,175 @@
+# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
+
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Caches
+
+.cache
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+# IntelliJ based IDEs
+.idea
+
+# Finder (MacOS) folder config
+.DS_Store

sepa-precios-archiver/README.md

@@ -0,0 +1,19 @@
+# sepa-precios-archiver
+
+Archivador del dataset de precios de [Precios Claros - Base SEPA](https://datos.produccion.gob.ar/dataset/sepa-precios). Recomprime para utilizar ~8 veces menos espacio, y resube a un bucket mio de Backblaze B2.
+
+## Instalación
+
+Para instalar las dependencias:
+
+```bash
+bun install
+```
+
+Para ejecutarlo:
+
+```bash
+bun run index.ts
+```
+
+This project was created using `bun init` in bun v1.1.25. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

sepa-precios-archiver/index.ts

@@ -0,0 +1,28 @@
+import { z } from "zod";
+import { zDatasetInfo } from "./schemas";
+import { mkdtemp, writeFile } from "fs/promises";
+import { $ } from "bun";
+
+const dir = await mkdtemp("/tmp/sepa-precios-archiver-");
+
+await $`git clone https://catdevnull:${process.env.GITHUB_TOKEN}@github.com/catdevnull/sepa-precios-metadata.git ${dir}`;
+
+async function getRawDatasetInfo() {
+  const response = await fetch(
+    "https://datos.produccion.gob.ar/api/3/action/package_show?id=sepa-precios",
+  );
+  const json = await response.json();
+  return json;
+}
+
+const rawDatasetInfo = await getRawDatasetInfo();
+const datasetInfo = z.object({ result: zDatasetInfo }).parse(rawDatasetInfo);
+
+await writeFile(
+  dir + "/dataset-info.json",
+  JSON.stringify(rawDatasetInfo, null, 2),
+);
+
+await $`cd ${dir} && git add dataset-info.json`;
+await $`cd ${dir} && git diff --staged --quiet || git commit -m "Update dataset info"`;
+await $`cd ${dir} && git push origin main`;

sepa-precios-archiver/package.json

@@ -0,0 +1,14 @@
+{
+  "name": "sepa-precios-archiver",
+  "module": "index.ts",
+  "type": "module",
+  "devDependencies": {
+    "@types/bun": "latest"
+  },
+  "peerDependencies": {
+    "typescript": "^5.0.0"
+  },
+  "dependencies": {
+    "zod": "^3.23.8"
+  }
+}

sepa-precios-archiver/schemas.ts

@@ -0,0 +1,17 @@
+import { z } from "zod";
+
+export const zDatasetInfo = z.object({
+  metadata_modified: z.coerce.date(),
+  metadata_created: z.coerce.date(),
+  resources: z.array(
+    z.object({
+      id: z.string(),
+      size: z.number(),
+      format: z.string(),
+      created: z.coerce.date(),
+      url: z.string(),
+      modified: z.coerce.date(),
+      description: z.string(),
+    }),
+  ),
+});

sepa-precios-archiver/tsconfig.json

@@ -0,0 +1,27 @@
+{
+  "compilerOptions": {
+    // Enable latest features
+    "lib": ["ESNext", "DOM"],
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleDetection": "force",
+    "jsx": "react-jsx",
+    "allowJs": true,
+
+    // Bundler mode
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "verbatimModuleSyntax": true,
+    "noEmit": true,
+
+    // Best practices
+    "strict": true,
+    "skipLibCheck": true,
+    "noFallthroughCasesInSwitch": true,
+
+    // Some stricter flags (disabled by default)
+    "noUnusedLocals": false,
+    "noUnusedParameters": false,
+    "noPropertyAccessFromIndexSignature": false
+  }
+}